Update README.md

README.md

@@ -9,10 +9,9 @@ tags:
 license: llama3.1
 ---
 
-# **L3.1-8B Hybrid: Stheno + Lunaris Merge**  
-**"Combining the Strengths of Two Llama3.3 Models"**
+# **Luminatium-L3-8b : Stheno + Lunaris Merge**  
 
-![image.png]
+![image/png]
 
 ---
 
@@ -22,7 +21,24 @@ This model was created using **SLERP (Spherical Linear Interpolation)**, a techn
 
 ### **Models Merged**  
 * [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2)  
-* [Sao10K/L3-8B-Lunaris-v1](https://huggingface.co/Sao10K/L3-8B-Lunaris-v1)  
+* [Sao10K/L3-8B-Lunaris-v1](https://huggingface.co/Sao10K/L3-8B-Lunaris-v1)
+
+---
+
+## **Recommended Settings**  
+```python
+temperature: 1.3  
+min_p: 0.08
+rep_pen : 1.1
+top_k : 50
+max_tokens/context : 8196
+```
+
+**Hardware Requirements:**  
+- Minimum: 16GB VRAM (Q4_K_M quantization recommended)  
+- Optimal: 32GB VRAM for full bfloat16 precision  
+
+---
 
 ### **Configuration**  
 ```yaml
@@ -46,29 +62,6 @@ parameters:
   - value: 0.5
 ```
 
----
-
-## **Recommended Settings**  
-```python
-temperature: 1.3  
-min_p: 0.08
-rep_pen : 1.1
-top_k : 50
-max_tokens/context : 8196
-```
-
-**Hardware Requirements:**  
-- Minimum: 16GB VRAM (Q4_K_M quantization recommended)  
-- Optimal: 32GB VRAM for full bfloat16 precision  
-
----
-
-## **Performance Highlights**  
-- **Balanced Capabilities**: Combines Stheno's technical expertise with Lunaris' conversational fluency  
-- **Versatile Use**: Suitable for coding, content creation, and general-purpose tasks  
-
----
-
 **This model was created using [mergekit](https://github.com/cg123/mergekit).**  
 **License: Llama3 (see LICENSE.md for details)**